github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #13170] Failed to concurrent call embed api #8708

New Issue
Open
opened 2026-04-12 21:28:52 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-12 21:28:52 -05:00
Owner
Copy Link

Originally created by @ultradawn on GitHub (Nov 20, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13170

Originally assigned to: @npardal on GitHub.

What is the issue?

ollama.error.rtf

Got 500 error when concurrent call embed api. refer to the detail into attached file

[GIN] 2025/11/20 - 13:56:55 | 500 | 1.274575125s | 127.0.0.1 | POST "/api/embed"
[GIN] 2025/11/20 - 13:56:55 | 500 | 1.264958458s | 127.0.0.1 | POST "/api/embed"

Relevant log output

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.13

Originally created by @ultradawn on GitHub (Nov 20, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13170 Originally assigned to: @npardal on GitHub. ### What is the issue? [ollama.error.rtf](https://github.com/user-attachments/files/23645321/ollama.error.rtf) Got 500 error when concurrent call embed api. refer to the detail into attached file ------------- [GIN] 2025/11/20 - 13:56:55 | 500 | 1.274575125s | 127.0.0.1 | POST "/api/embed" [GIN] 2025/11/20 - 13:56:55 | 500 | 1.264958458s | 127.0.0.1 | POST "/api/embed" ### Relevant log output ```shell ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.13
GiteaMirror added the bug label 2026-04-12 21:28:52 -05:00
GiteaMirror commented 2026-04-12 21:28:53 -05:00
Author
Owner
Copy Link

@ultradawn commented on GitHub (Nov 20, 2025):

Macbook Pro M4

<!-- gh-comment-id:3556131605 --> @ultradawn commented on GitHub (Nov 20, 2025): Macbook Pro M4
GiteaMirror commented 2026-04-12 21:28:53 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Nov 21, 2025):

Looking through the log, I think is related to truncation and not specifically concurrent requests.

init: embeddings required but some input tokens were not marked as outputs -> overriding\
SIGABRT: abort\
PC=0x1986da388 m=10 sigcode=0\
signal arrived during cgo execution\
\
goroutine 7 gp=0x14000582380 m=10 mp=0x14000680008 [syscall]:\
runtime.cgocall(0x100fc1148, 0x140000dcb58)\
        runtime/cgocall.go:167 +0x44 fp=0x140000dcb20 sp=0x140000dcae0 pc=0x1004be684\
github.com/ollama/ollama/llama._Cfunc_llama_decode(0x12d60a620, \{0x6a, 0x12a013800, 0x0, 0x12a014000, 0x12a014800, 0x12a044600, 0x12d704ba0\})\
        _cgo_gotypes.go:674 +0x30 fp=0x140000dcb50 sp=0x140000dcb20 pc=0x100805e50\
github.com/ollama/ollama/llama.(*Context).Decode.func1(...)\
        github.com/ollama/ollama/llama/llama.go:168\
github.com/ollama/ollama/llama.(*Context).Decode(0x1400032d208?, 0x1004c1e98?)\
        github.com/ollama/ollama/llama/llama.go:168 +0xcc fp=0x140000dcc40 sp=0x140000dcb50 pc=0x1008080dc\
github.com/ollama/ollama/runner/llamarunner.(*Server).processBatch(0x140000ea140, 0x1400038f2c0, 0x140000dcf18)\
        github.com/ollama/ollama/runner/llamarunner/runner.go:493 +0x1d4 fp=0x140000dced0 sp=0x140000dcc40 pc=0x1008a46b4\
github.com/ollama/ollama/runner/llamarunner.(*Server).run(0x140000ea140, \{0x1016dccc0, 0x1400017cb90\})\
        github.com/ollama/ollama/runner/llamarunner/runner.go:386 +0x15c fp=0x140000dcfa0 sp=0x140000dced0 pc=0x1008a437c\
github.com/ollama/ollama/runner/llamarunner.Execute.gowrap1()\
        github.com/ollama/ollama/runner/llamarunner/runner.go:979 +0x2c fp=0x140000dcfd0 sp=0x140000dcfa0 pc=0x1008a848c\
runtime.goexit(\{\})\
        runtime/asm_arm64.s:1268 +0x4 fp=0x140000dcfd0 sp=0x140000dcfd0 pc=0x1004c9d04\
created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1\
        github.com/ollama/ollama/runner/llamarunner/runner.go:979 +0x418\
\
<!-- gh-comment-id:3564703030 --> @pdevine commented on GitHub (Nov 21, 2025): Looking through the log, I think is related to truncation and not specifically concurrent requests. ``` init: embeddings required but some input tokens were not marked as outputs -> overriding\ SIGABRT: abort\ PC=0x1986da388 m=10 sigcode=0\ signal arrived during cgo execution\ \ goroutine 7 gp=0x14000582380 m=10 mp=0x14000680008 [syscall]:\ runtime.cgocall(0x100fc1148, 0x140000dcb58)\ runtime/cgocall.go:167 +0x44 fp=0x140000dcb20 sp=0x140000dcae0 pc=0x1004be684\ github.com/ollama/ollama/llama._Cfunc_llama_decode(0x12d60a620, \{0x6a, 0x12a013800, 0x0, 0x12a014000, 0x12a014800, 0x12a044600, 0x12d704ba0\})\ _cgo_gotypes.go:674 +0x30 fp=0x140000dcb50 sp=0x140000dcb20 pc=0x100805e50\ github.com/ollama/ollama/llama.(*Context).Decode.func1(...)\ github.com/ollama/ollama/llama/llama.go:168\ github.com/ollama/ollama/llama.(*Context).Decode(0x1400032d208?, 0x1004c1e98?)\ github.com/ollama/ollama/llama/llama.go:168 +0xcc fp=0x140000dcc40 sp=0x140000dcb50 pc=0x1008080dc\ github.com/ollama/ollama/runner/llamarunner.(*Server).processBatch(0x140000ea140, 0x1400038f2c0, 0x140000dcf18)\ github.com/ollama/ollama/runner/llamarunner/runner.go:493 +0x1d4 fp=0x140000dced0 sp=0x140000dcc40 pc=0x1008a46b4\ github.com/ollama/ollama/runner/llamarunner.(*Server).run(0x140000ea140, \{0x1016dccc0, 0x1400017cb90\})\ github.com/ollama/ollama/runner/llamarunner/runner.go:386 +0x15c fp=0x140000dcfa0 sp=0x140000dced0 pc=0x1008a437c\ github.com/ollama/ollama/runner/llamarunner.Execute.gowrap1()\ github.com/ollama/ollama/runner/llamarunner/runner.go:979 +0x2c fp=0x140000dcfd0 sp=0x140000dcfa0 pc=0x1008a848c\ runtime.goexit(\{\})\ runtime/asm_arm64.s:1268 +0x4 fp=0x140000dcfd0 sp=0x140000dcfd0 pc=0x1004c9d04\ created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1\ github.com/ollama/ollama/runner/llamarunner/runner.go:979 +0x418\ \ ```
GiteaMirror commented 2026-04-12 21:28:54 -05:00
Author
Owner
Copy Link

@jessegross commented on GitHub (Nov 25, 2025):

Probably another batch size issue, similar to https://github.com/ollama/ollama/issues/13054

<!-- gh-comment-id:3573365308 --> @jessegross commented on GitHub (Nov 25, 2025): Probably another batch size issue, similar to https://github.com/ollama/ollama/issues/13054
GiteaMirror commented 2026-04-12 21:28:54 -05:00
Author
Owner
Copy Link

@ultradawn commented on GitHub (Nov 27, 2025):

I have to downgrade the version 0.11.11 to solve this issue. I suppose it's bug after v.0.11 @jessegross @pdevine

<!-- gh-comment-id:3584198093 --> @ultradawn commented on GitHub (Nov 27, 2025): I have to downgrade the version 0.11.11 to solve this issue. I suppose it's bug after v.0.11 @jessegross @pdevine
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#8708
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?